• Title/Summary/Keyword: temporal lag

Search Result 41, Processing Time 0.015 seconds

Exploring the Temporal Relationship Between Traffic Information Web/Mobile Application Access and Actual Traffic Volume on Expressways (웹/모바일-어플리케이션 접속 지표와 TCS 교통량의 상관관계 연구)

  • RYU, Ingon;LEE, Jaeyoung;CHOI, Keechoo;KIM, Junghwa;AHN, Soonwook
    • Journal of Korean Society of Transportation
    • /
    • v.34 no.1
    • /
    • pp.1-14
    • /
    • 2016
  • In the recent years, the internet has become accessible without limitation of time and location to anyone with smartphones. It resulted in more convenient travel information access both on the pre-trip and en-route phase. The main objective of this study is to conduct a stationary test for traffic information web/mobile application access indexes from TCS (Toll Collection System); and analyzing the relationship between the web/mobile application access indexes and actual traffic volume on expressways, in order to analyze searching behavior of expressway related travel information. The key findings of this study are as follows: first, the results of ADF-test and PP-test confirm that the web/mobile application access indexes by time periods satisfy stationary conditions even without log or differential transformation. Second, the Pearson correlation test showed that there is a strong and positive correlation between the web/mobile application access indexes and expressway entry and exit traffic volume. In contrast, truck entry traffic volume from TCS has no significant correlation with the web/mobile application access indexes. Third, the time gap relationship between time-series variables (i.e., concurrent, leading and lagging) was analyzed by cross-correlation tests. The results indicated that the mobile application access leads web access, and the number of mobile application execution is concurrent with all web access indexes. Lastly, there was no web/mobile application access indexes leading expressway entry traffic volumes on expressways, and the highest correlation was observed between webpage view/visitor/new visitor/repeat visitor/application execution counts and expressway entry volume with a lag of one hour. It is expected that specific individual travel behavior can be predicted such as route conversion time and ratio if the data are subdivided by time periods and areas and utilizing traffic information users' location.